Best computer vision skills for Claude Code, Codex and other agents.

Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

Orchestra-Research/AI-Research-SKILLs

Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

Orchestra-Research/AI-Research-SKILLs

Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

liustack/modlens

A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.

Tencent/YOLO-Master

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk.

jjyaoao/HelloAgents

Composites several moments from real drone footage into one still with ghost trails, then lays out paper figures and an editable PowerPoint file.

XXLiu-HNU/visualize_uav_trajectory

Trains and evaluates several WiFi-signal-based pose and sensing models, from unsupervised pose estimation to domain adaptation and publishing.

ruvnet/RuView

Adds a new local feature matching model from a GitHub repository to the image-matching-webui project as a working WebUI option.

Vincentqyw/image-matching-webui

Pixel-based motion and UI change analysis from frame sequences or screenshots using computer vision and visual comparison.

edwardsanchez/MotionEyes

Guide to LLaVA for image chat, visual question answering and captioning, with model sizes, CLI and Gradio usage and multi-turn conversation code.

Orchestra-Research/AI-Research-SKILLs

Generate a specialized domain-expert research agent modeled on PaperClaw architecture.

guhaohao0991/PaperClaw

Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

huggingface/skills

Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

SharpAI/DeepCamera

This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but…

fcakyon/claude-codex-settings

Policy for AlbumentationsX transforms that combine multiple images or objects.

albumentations-team/AlbumentationsX

Command-line access to Z.AI vision analysis, web search, page reading and GitHub repo exploration through npx zai-cli, using an API key.

numman-ali/zai-cli

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

xiincs/claude-code-vision-skill

Query images with a local Ollama vision model without loading the image into the main agent context.

gridaco/grida

Track, retrieve, screen, and synthesize research frontiers for geospatial AI, remote sensing big data, and transferable computer vision methods.

limi124/remote-sensing-research-radar

YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

SharpAI/DeepCamera

Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs.

waybarrios/opencode-power-pack

Train a custom VideoHighlighter action or object model from a few videos the user provides — cut into samples, sort with CLIP, review contact sheets, build, train, install only if better.

Aseiel/VideoHighlighter

Regression test the OpenClaw Codex App Server plugin against a live local OpenClaw instance in Telegram or Discord.

pwrdrvr/openclaw-codex-app-server

Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference.

drpwchen/textbook-to-note

Calls an external vision model through vision.js to analyze an image when the user explicitly invokes /skill luma-vision, for agents whose own model cannot see images.

JochenYang/luma-mcp

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

SharpAI/DeepCamera

Low-level SenseNova tools for image generation, image editing, image recognition with a VLM and text optimization with an LLM, meant to be called by higher-level skills rather than directly.

OpenSenseNova/SenseNova-Skills

Systematic performance audit for AlbumentationsX runtime code.

albumentations-team/AlbumentationsX

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison.

einverne/dotfiles

Google Coral Edge TPU — real-time object detection natively via Windows WSL

SharpAI/DeepCamera

Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling.

intel/auto-round

Vision-language pre-training framework bridging frozen image encoders and LLMs.

Orchestra-Research/AI-Research-SKILLs

Extracts pixel, video-frame, speech, music and visual-semantic features from image, video and audio files for research datasets, using local tools or the Gemini API.

TyrealQ/q-skills

Agent-only decision procedure for ask-user findings. An agent skill from kunchenguid/firstmate.

kunchenguid/firstmate

Core ML, Create ML, Vision framework, Natural Language framework, on-device ML integration.

gustavscirulis/snapgrid

Processes digital pathology whole slide images with histolab: tissue detection, mask creation, tile extraction and dataset preparation for deep learning.

davila7/claude-code-templates

Loads pre-trained Hugging Face Transformers models for text, vision and audio tasks, runs inference with pipelines and fine-tunes on custom datasets.

davila7/claude-code-templates

OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU)

SharpAI/DeepCamera

把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief. An agent skill from zenstory-ai/video-recap-skills.

zenstory-ai/video-recap-skills

Generate text, have conversations, write code, reason, and call functions with Qwen models.

QianWen-AI/qianwen-ai

Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

NVIDIA/skills

Full checklist for adding a new transform to AlbumentationsX.

albumentations-team/AlbumentationsX

Review screenshots or other images with OpenRouter vision models via bundled Deno scripts.

mizchi/skills

Extracts body and hand keypoint trajectories from an authorized reference video, with skeleton previews and confidence data, for pose reference or motion control input.

Pluviobyte/rnskill

Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

NVIDIA/skills

Review public AlbumentationsX docstrings for useful descriptions, runnable examples, parameter semantics, and related transforms.

albumentations-team/AlbumentationsX

CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.

nanoAgentTeam/research-claw

Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups.

arpitg1304/robotics-agent-skills